Towards User Transparent Parallel Multimedia Computing on GPU-Clusters

Abstract

Abstract. The research area of Multimedia Content Analysis (MMCA) considers all aspects of the automated extraction of knowledge from multimedia archives and data streams. To satisfy the increasing computational demands of MMCA problems, the use of High Performance Computing (HPC) techniques is essential. As most MMCA researchers are not HPC experts, there is an urgent need for 'familiar' programming models and tools that are both easy to use and efficient. Today, several user transparent library-based parallelization tools exist that aim to satisfy both these requirements. In general, such tools focus on data parallel execution on traditional compute clusters. As of yet, none of these tools also incorporate the use of many-core processors (e.g. GPUs), however. While traditional clusters are now being transformed into GPU-clusters, programming complexity vastly increases -and the need for easy and efficient programming models is as urgent as ever. This paper presents our first steps in the direction of obtaining a user transparent programming model for data parallel and hierarchical multimedia computing on GPU-clusters. The model is obtained by extending an existing user transparent parallel programming system (applicable to traditional compute clusters) with a set of CUDA compute kernels. We show our model to be capable of obtaining orders-of-magnitude speed improvements, without requiring any additional effort from the application programmer.

User Transparent Data and Task Parallel Multimedia Computing with Pyxis-DT

“…In the near future, we aim to integrate support for such hardware architectures by integrating alternative implementations for the sequential compute kernels -for example following our recently developed GPU-cluster-based implementation for Parallel-Horus [15].…”

“…An interesting additional feature of the system is that -next to data parallel execution on clusters -the parallel engine also supports running any task on a GPU (if a CUDA-based implementation for such a task is available). In the very near future we also intend to integrate our recent GPU-cluster based implementation of Parallel-Horus [15] into Pyxis-DT.…”

Lessons Learned in a Decade of Research Software Engineering GPU Applications

“…Parallel-Horus [34] is an image processing library that automatically parallelizes image algebra operations. One of the more challenging aspects in integrating GPU kernels was to deal with the separate GPU memory.…”

Jungle Computing: Distributed Supercomputing Beyond Clusters, Grids, and Clouds

“…In other words, with this approach we obtain a system that can execute sequential Jorus applications in data parallel fashion, while exploiting the power of GPU hardware. The details of the CUDA-implemented compute kernels are beyond the scope of this chapter, and are discussed further in [52].…”